New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Documentation Enhancement Request: Example of Spectral Clustering for a graph #9481
Comments
could you point to a dataset, please?
…On 3 Aug 2017 3:05 am, "Alexander Lenail" ***@***.***> wrote:
Spectral Clustering is one of the primary ways of clustering graphs. It
would very helpful to document a recipe for using this code to cluster
graphs.
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#9481>, or mute the
thread
<https://github.com/notifications/unsubscribe-auth/AAEz68Waq6555tQI7Ux_4zDaE1xWG4ydks5sUKxVgaJpZM4OrYyY>
.
|
The "Iris Dataset" in the graph theory world is called the Karate Club Dataset. It's quite small, and the goal should be to predict two clusters. Libraries like networkx include this graph as a method. |
@jnothman bump |
@jnothman I would love to do this myself, but that's just it -- I'm don't know how to use spectral clustering from this library for graphs. If you give me the general gist, i can experiment and figure it out myself perhaps, and then try to write this documentation. Let me know. |
(Coming from the StackOverflow-question by the author) I tried to approach the karate-club task with Spectral-Clustering with minimal knowledge and only using sklearn's docs and some definition of Normalized Graph Cuts (to see if that's what we want; yes). See above link for more information. Tuning If someone thinks about adding an example, one probably has to think if this dataset should be somehow included (as i'm taking it from networkx).
Output:
|
Spectral Clustering is one of the primary ways of clustering graphs. It would very helpful to document a recipe for using this code to cluster graphs.
The text was updated successfully, but these errors were encountered: